Uncertainty Estimates for Optical Flow with Multi-Hypotheses Networks

02/20/2018
by   Eddy Ilg, et al.
0

Recent work has shown that optical flow estimation can be formulated as an end-to-end supervised learning problem, which yields estimates with a superior accuracy-runtime tradeoff compared to alternative methodology. In this paper, we make the network estimate its local uncertainty about the correctness of its prediction, which is vital information when building decisions on top of the estimated optical flow. For the first time we compare several strategies and techniques to estimate uncertainty in a large-scale computer vision task like optical flow estimation. Moreover, we introduce a new network architecture that enforces complementary hypotheses and provides uncertainty estimates efficiently within a single forward pass without the need for sampling or ensembles. We demonstrate high-quality uncertainty estimates that clearly improve over previous confidence measures on optical flow and allow for interactive frame rates.

READ FULL TEXT

page 1

page 8

page 14

page 15

page 16

page 17

page 18

page 19

research
12/06/2016

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

The FlowNet demonstrated that optical flow estimation can be cast as a l...
research
04/16/2021

OmniFlow: Human Omnidirectional Optical Flow

Optical flow is the motion of a pixel between at least two consecutive v...
research
12/12/2016

Hybrid Learning of Optical Flow and Next Frame Prediction to Boost Optical Flow in the Wild

CNN-based optical flow estimation has attracted attention recently, main...
research
01/24/2019

Never Forget: Balancing Exploration and Exploitation via Learning Optical Flow

Exploration bonus derived from the novelty of the states in an environme...
research
11/04/2016

Statistical Inverse Formulation of Optical Flow with Uncertainty Quantification

Optical flow refers to the visual motion observed between two consecutiv...
research
10/21/2021

SLURP: Side Learning Uncertainty for Regression Problems

It has become critical for deep learning algorithms to quantify their ou...
research
01/19/2018

What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation?

The finding that very large networks can be trained efficiently and reli...

Please sign up or login with your details

Forgot password? Click here to reset